From 61aa940074da0ec60a105f1ab45b45bc9815633d Mon Sep 17 00:00:00 2001
From: Alex Bradbury <asb@lowrisc.org>
Date: Sat, 12 Jan 2019 07:43:06 +0000
Subject: [PATCH] [RISCV] Introduce codegen patterns for RV64M-only
 instructions

As discussed on llvm-dev
<http://lists.llvm.org/pipermail/llvm-dev/2018-December/128497.html>, we have
to be careful when trying to select the *w RV64M instructions. i32 is not a
legal type for RV64 in the RISC-V backend, so operations have been promoted by
the time they reach instruction selection. Information about whether the
operation was originally a 32-bit operations has been lost, and it's easy to
write incorrect patterns.

Similarly to the variable 32-bit shifts, a DAG combine on ANY_EXTEND will
produce a SIGN_EXTEND if this is likely to result in sdiv/udiv/urem being
selected (and so save instructions to sext/zext the input operands).

Differential Revision: https://reviews.llvm.org/D53230

llvm-svn: 350993
---
 llvm/lib/Target/RISCV/RISCVISelLowering.cpp        |   26 +-
 llvm/lib/Target/RISCV/RISCVInstrInfoM.td           |   31 +
 llvm/test/CodeGen/RISCV/div.ll                     |  251 ++++
 llvm/test/CodeGen/RISCV/mul.ll                     |  136 +-
 llvm/test/CodeGen/RISCV/rem.ll                     |   38 +
 .../test/CodeGen/RISCV/rv64m-exhaustive-w-insts.ll | 1308 ++++++++++++++++++++
 6 files changed, 1781 insertions(+), 9 deletions(-)
 create mode 100644 llvm/test/CodeGen/RISCV/rv64m-exhaustive-w-insts.ll

diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index ca6fbb1..508dcbd 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -525,6 +525,20 @@ static bool isVariableShift(SDValue Val) {
   }
 }
 
+// Returns true if the given node is an sdiv, udiv, or urem with non-constant
+// operands.
+static bool isVariableSDivUDivURem(SDValue Val) {
+  switch (Val.getOpcode()) {
+  default:
+    return false;
+  case ISD::SDIV:
+  case ISD::UDIV:
+  case ISD::UREM:
+    return Val.getOperand(0).getOpcode() != ISD::Constant &&
+           Val.getOperand(1).getOpcode() != ISD::Constant;
+  }
+}
+
 SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
                                                DAGCombinerInfo &DCI) const {
   SelectionDAG &DAG = DCI.DAG;
@@ -552,12 +566,14 @@ SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
         N, DAG.getNode(N->getOpcode(), DL, LHS.getValueType(), LHS, NewRHS));
   }
   case ISD::ANY_EXTEND: {
-    // If any-extending an i32 variable-length shift to i64, then instead
-    // sign-extend in order to increase the chance of being able to select the
-    // sllw/srlw/sraw instruction.
+    // If any-extending an i32 variable-length shift or sdiv/udiv/urem to i64,
+    // then instead sign-extend in order to increase the chance of being able
+    // to select the sllw/srlw/sraw/divw/divuw/remuw instructions.
     SDValue Src = N->getOperand(0);
-    if (N->getValueType(0) != MVT::i64 || Src.getValueType() != MVT::i32 ||
-        !isVariableShift(Src))
+    if (N->getValueType(0) != MVT::i64 || Src.getValueType() != MVT::i32)
+      break;
+    if (!isVariableShift(Src) &&
+        !(Subtarget.hasStdExtM() && isVariableSDivUDivURem(Src)))
       break;
     SDLoc DL(N);
     return DCI.CombineTo(N, DAG.getNode(ISD::SIGN_EXTEND, DL, MVT::i64, Src));
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoM.td b/llvm/lib/Target/RISCV/RISCVInstrInfoM.td
index 2dd10ad..05dd331 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoM.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoM.td
@@ -49,3 +49,34 @@ def : PatGprGpr<udiv, DIVU>;
 def : PatGprGpr<srem, REM>;
 def : PatGprGpr<urem, REMU>;
 } // Predicates = [HasStdExtM]
+
+let Predicates = [HasStdExtM, IsRV64] in {
+def : Pat<(sext_inreg (mul GPR:$rs1, GPR:$rs2), i32),
+          (MULW GPR:$rs1, GPR:$rs2)>;
+def : Pat<(sext_inreg (sdiv (sexti32 GPR:$rs1),
+                            (sexti32 GPR:$rs2)), i32),
+          (DIVW GPR:$rs1, GPR:$rs2)>;
+def : Pat<(zexti32 (sdiv (sexti32 GPR:$rs1),
+                         (sexti32 GPR:$rs2))),
+          (SRLI (SLLI (DIVW GPR:$rs1, GPR:$rs2), 32), 32)>;
+def : Pat<(sext_inreg (udiv (zexti32 GPR:$rs1), (zexti32 GPR:$rs2)), i32),
+          (DIVUW GPR:$rs1, GPR:$rs2)>;
+// It's cheaper to perform a divuw and zero-extend the result than to
+// zero-extend both inputs to a udiv.
+def : Pat<(udiv (and GPR:$rs1, 0xffffffff), (and GPR:$rs2, 0xffffffff)),
+          (SRLI (SLLI (DIVUW GPR:$rs1, GPR:$rs2), 32), 32)>;
+// Although the sexti32 operands may not have originated from an i32 srem,
+// this pattern is safe as it is impossible for two sign extended inputs to
+// produce a result where res[63:32]=0 and res[31]=1.
+def : Pat<(srem (sexti32 GPR:$rs1), (sexti32 GPR:$rs2)),
+          (REMW GPR:$rs1, GPR:$rs2)>;
+def : Pat<(sext_inreg (srem (sexti32 GPR:$rs1),
+                            (sexti32 GPR:$rs2)), i32),
+          (REMW GPR:$rs1, GPR:$rs2)>;
+def : Pat<(sext_inreg (urem (zexti32 GPR:$rs1), (zexti32 GPR:$rs2)), i32),
+          (REMUW GPR:$rs1, GPR:$rs2)>;
+// It's cheaper to perform a remuw and zero-extend the result than to
+// zero-extend both inputs to a urem.
+def : Pat<(urem (and GPR:$rs1, 0xffffffff), (and GPR:$rs2, 0xffffffff)),
+          (SRLI (SLLI (REMUW GPR:$rs1, GPR:$rs2), 32), 32)>;
+} // Predicates = [HasStdExtM, IsRV64]
diff --git a/llvm/test/CodeGen/RISCV/div.ll b/llvm/test/CodeGen/RISCV/div.ll
index da9df17..1fd0084 100644
--- a/llvm/test/CodeGen/RISCV/div.ll
+++ b/llvm/test/CodeGen/RISCV/div.ll
@@ -3,6 +3,10 @@
 ; RUN:   | FileCheck -check-prefix=RV32I %s
 ; RUN: llc -mtriple=riscv32 -mattr=+m -verify-machineinstrs < %s \
 ; RUN:   | FileCheck -check-prefix=RV32IM %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64IM %s
 
 define i32 @udiv(i32 %a, i32 %b) nounwind {
 ; RV32I-LABEL: udiv:
@@ -18,6 +22,24 @@ define i32 @udiv(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    divu a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: udiv:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    slli a1, a1, 32
+; RV64I-NEXT:    srli a1, a1, 32
+; RV64I-NEXT:    call __udivdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: udiv:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = udiv i32 %a, %b
   ret i32 %1
 }
@@ -40,6 +62,34 @@ define i32 @udiv_constant(i32 %a) nounwind {
 ; RV32IM-NEXT:    mulhu a0, a0, a1
 ; RV32IM-NEXT:    srli a0, a0, 2
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: udiv_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __udivdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: udiv_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    lui a1, 1035469
+; RV64IM-NEXT:    addiw a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    mulhu a0, a0, a1
+; RV64IM-NEXT:    srli a0, a0, 2
+; RV64IM-NEXT:    ret
   %1 = udiv i32 %a, 5
   ret i32 %1
 }
@@ -54,6 +104,16 @@ define i32 @udiv_pow2(i32 %a) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    srli a0, a0, 3
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: udiv_pow2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    srliw a0, a0, 3
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: udiv_pow2:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    srliw a0, a0, 3
+; RV64IM-NEXT:    ret
   %1 = udiv i32 %a, 8
   ret i32 %1
 }
@@ -76,6 +136,20 @@ define i64 @udiv64(i64 %a, i64 %b) nounwind {
 ; RV32IM-NEXT:    lw ra, 12(sp)
 ; RV32IM-NEXT:    addi sp, sp, 16
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: udiv64:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __udivdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: udiv64:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = udiv i64 %a, %b
   ret i64 %1
 }
@@ -102,6 +176,30 @@ define i64 @udiv64_constant(i64 %a) nounwind {
 ; RV32IM-NEXT:    lw ra, 12(sp)
 ; RV32IM-NEXT:    addi sp, sp, 16
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: udiv64_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __udivdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: udiv64_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    lui a1, 1035469
+; RV64IM-NEXT:    addiw a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, -819
+; RV64IM-NEXT:    mulhu a0, a0, a1
+; RV64IM-NEXT:    srli a0, a0, 2
+; RV64IM-NEXT:    ret
   %1 = udiv i64 %a, 5
   ret i64 %1
 }
@@ -120,6 +218,22 @@ define i32 @sdiv(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    div a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    sext.w a1, a1
+; RV64I-NEXT:    call __divdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = sdiv i32 %a, %b
   ret i32 %1
 }
@@ -144,6 +258,34 @@ define i32 @sdiv_constant(i32 %a) nounwind {
 ; RV32IM-NEXT:    srai a0, a0, 1
 ; RV32IM-NEXT:    add a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __divdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    sext.w a0, a0
+; RV64IM-NEXT:    lui a1, 13107
+; RV64IM-NEXT:    addiw a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 13
+; RV64IM-NEXT:    addi a1, a1, 1639
+; RV64IM-NEXT:    mulh a0, a0, a1
+; RV64IM-NEXT:    srli a1, a0, 63
+; RV64IM-NEXT:    srai a0, a0, 1
+; RV64IM-NEXT:    add a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = sdiv i32 %a, 5
   ret i32 %1
 }
@@ -164,6 +306,24 @@ define i32 @sdiv_pow2(i32 %a) nounwind {
 ; RV32IM-NEXT:    add a0, a0, a1
 ; RV32IM-NEXT:    srai a0, a0, 3
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv_pow2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    sext.w a1, a0
+; RV64I-NEXT:    srli a1, a1, 60
+; RV64I-NEXT:    andi a1, a1, 7
+; RV64I-NEXT:    add a0, a0, a1
+; RV64I-NEXT:    sraiw a0, a0, 3
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv_pow2:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    sext.w a1, a0
+; RV64IM-NEXT:    srli a1, a1, 60
+; RV64IM-NEXT:    andi a1, a1, 7
+; RV64IM-NEXT:    add a0, a0, a1
+; RV64IM-NEXT:    sraiw a0, a0, 3
+; RV64IM-NEXT:    ret
   %1 = sdiv i32 %a, 8
   ret i32 %1
 }
@@ -186,6 +346,20 @@ define i64 @sdiv64(i64 %a, i64 %b) nounwind {
 ; RV32IM-NEXT:    lw ra, 12(sp)
 ; RV32IM-NEXT:    addi sp, sp, 16
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv64:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __divdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv64:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    div a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = sdiv i64 %a, %b
   ret i64 %1
 }
@@ -212,6 +386,83 @@ define i64 @sdiv64_constant(i64 %a) nounwind {
 ; RV32IM-NEXT:    lw ra, 12(sp)
 ; RV32IM-NEXT:    addi sp, sp, 16
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv64_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __divdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv64_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    lui a1, 13107
+; RV64IM-NEXT:    addiw a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 12
+; RV64IM-NEXT:    addi a1, a1, 819
+; RV64IM-NEXT:    slli a1, a1, 13
+; RV64IM-NEXT:    addi a1, a1, 1639
+; RV64IM-NEXT:    mulh a0, a0, a1
+; RV64IM-NEXT:    srli a1, a0, 63
+; RV64IM-NEXT:    srai a0, a0, 1
+; RV64IM-NEXT:    add a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = sdiv i64 %a, 5
   ret i64 %1
 }
+
+; Although this sdiv has two sexti32 operands, it shouldn't compile to divw on
+; RV64M as that wouldn't produce the correct result for e.g. INT_MIN/-1.
+
+define i64 @sdiv64_sext_operands(i32 %a, i32 %b) nounwind {
+; RV32I-LABEL: sdiv64_sext_operands:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi sp, sp, -16
+; RV32I-NEXT:    sw ra, 12(sp)
+; RV32I-NEXT:    mv a2, a1
+; RV32I-NEXT:    srai a1, a0, 31
+; RV32I-NEXT:    srai a3, a2, 31
+; RV32I-NEXT:    call __divdi3
+; RV32I-NEXT:    lw ra, 12(sp)
+; RV32I-NEXT:    addi sp, sp, 16
+; RV32I-NEXT:    ret
+;
+; RV32IM-LABEL: sdiv64_sext_operands:
+; RV32IM:       # %bb.0:
+; RV32IM-NEXT:    addi sp, sp, -16
+; RV32IM-NEXT:    sw ra, 12(sp)
+; RV32IM-NEXT:    mv a2, a1
+; RV32IM-NEXT:    srai a1, a0, 31
+; RV32IM-NEXT:    srai a3, a2, 31
+; RV32IM-NEXT:    call __divdi3
+; RV32IM-NEXT:    lw ra, 12(sp)
+; RV32IM-NEXT:    addi sp, sp, 16
+; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: sdiv64_sext_operands:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    sext.w a1, a1
+; RV64I-NEXT:    call __divdi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: sdiv64_sext_operands:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    sext.w a1, a1
+; RV64IM-NEXT:    sext.w a0, a0
+; RV64IM-NEXT:    div a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sext i32 %a to i64
+  %2 = sext i32 %b to i64
+  %3 = sdiv i64 %1, %2
+  ret i64 %3
+}
diff --git a/llvm/test/CodeGen/RISCV/mul.ll b/llvm/test/CodeGen/RISCV/mul.ll
index 444a75f..9bf95be 100644
--- a/llvm/test/CodeGen/RISCV/mul.ll
+++ b/llvm/test/CodeGen/RISCV/mul.ll
@@ -3,8 +3,12 @@
 ; RUN:   | FileCheck -check-prefix=RV32I %s
 ; RUN: llc -mtriple=riscv32 -mattr=+m -verify-machineinstrs < %s \
 ; RUN:   | FileCheck -check-prefix=RV32IM %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64IM %s
 
-define i32 @square(i32 %a) nounwind {
+define signext i32 @square(i32 %a) nounwind {
 ; RV32I-LABEL: square:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
@@ -19,11 +23,27 @@ define i32 @square(i32 %a) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    mul a0, a0, a0
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: square:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    mv a1, a0
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: square:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a0
+; RV64IM-NEXT:    ret
   %1 = mul i32 %a, %a
   ret i32 %1
 }
 
-define i32 @mul(i32 %a, i32 %b) nounwind {
+define signext i32 @mul(i32 %a, i32 %b) nounwind {
 ; RV32I-LABEL: mul:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
@@ -37,11 +57,26 @@ define i32 @mul(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    mul a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mul:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mul:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = mul i32 %a, %b
   ret i32 %1
 }
 
-define i32 @mul_constant(i32 %a) nounwind {
+define signext i32 @mul_constant(i32 %a) nounwind {
 ; RV32I-LABEL: mul_constant:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
@@ -57,6 +92,23 @@ define i32 @mul_constant(i32 %a) nounwind {
 ; RV32IM-NEXT:    addi a1, zero, 5
 ; RV32IM-NEXT:    mul a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mul_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mul_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    addi a1, zero, 5
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = mul i32 %a, 5
   ret i32 %1
 }
@@ -71,6 +123,16 @@ define i32 @mul_pow2(i32 %a) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    slli a0, a0, 3
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mul_pow2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    slli a0, a0, 3
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mul_pow2:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 3
+; RV64IM-NEXT:    ret
   %1 = mul i32 %a, 8
   ret i32 %1
 }
@@ -94,6 +156,20 @@ define i64 @mul64(i64 %a, i64 %b) nounwind {
 ; RV32IM-NEXT:    add a1, a3, a1
 ; RV32IM-NEXT:    mul a0, a0, a2
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mul64:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mul64:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = mul i64 %a, %b
   ret i64 %1
 }
@@ -118,6 +194,22 @@ define i64 @mul64_constant(i64 %a) nounwind {
 ; RV32IM-NEXT:    add a1, a3, a1
 ; RV32IM-NEXT:    mul a0, a0, a2
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mul64_constant:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    addi a1, zero, 5
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mul64_constant:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    addi a1, zero, 5
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = mul i64 %a, 5
   ret i64 %1
 }
@@ -140,6 +232,26 @@ define i32 @mulhs(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    mulh a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mulhs:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    sext.w a1, a1
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mulhs:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    sext.w a1, a1
+; RV64IM-NEXT:    sext.w a0, a0
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
   %1 = sext i32 %a to i64
   %2 = sext i32 %b to i64
   %3 = mul i64 %1, %2
@@ -148,7 +260,7 @@ define i32 @mulhs(i32 %a, i32 %b) nounwind {
   ret i32 %5
 }
 
-define i32 @mulhu(i32 %a, i32 %b) nounwind {
+define zeroext i32 @mulhu(i32 zeroext %a, i32 zeroext %b) nounwind {
 ; RV32I-LABEL: mulhu:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi sp, sp, -16
@@ -166,6 +278,22 @@ define i32 @mulhu(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    mulhu a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: mulhu:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __muldi3
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: mulhu:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
   %1 = zext i32 %a to i64
   %2 = zext i32 %b to i64
   %3 = mul i64 %1, %2
diff --git a/llvm/test/CodeGen/RISCV/rem.ll b/llvm/test/CodeGen/RISCV/rem.ll
index f37931f..505a351 100644
--- a/llvm/test/CodeGen/RISCV/rem.ll
+++ b/llvm/test/CodeGen/RISCV/rem.ll
@@ -3,6 +3,10 @@
 ; RUN:   | FileCheck -check-prefix=RV32I %s
 ; RUN: llc -mtriple=riscv32 -mattr=+m -verify-machineinstrs < %s \
 ; RUN:   | FileCheck -check-prefix=RV32IM %s
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64IM %s
 
 define i32 @urem(i32 %a, i32 %b) nounwind {
 ; RV32I-LABEL: urem:
@@ -18,6 +22,24 @@ define i32 @urem(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    remu a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: urem:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    slli a1, a1, 32
+; RV64I-NEXT:    srli a1, a1, 32
+; RV64I-NEXT:    call __umoddi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: urem:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = urem i32 %a, %b
   ret i32 %1
 }
@@ -36,6 +58,22 @@ define i32 @srem(i32 %a, i32 %b) nounwind {
 ; RV32IM:       # %bb.0:
 ; RV32IM-NEXT:    rem a0, a0, a1
 ; RV32IM-NEXT:    ret
+;
+; RV64I-LABEL: srem:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    sext.w a1, a1
+; RV64I-NEXT:    call __moddi3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+;
+; RV64IM-LABEL: srem:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
   %1 = srem i32 %a, %b
   ret i32 %1
 }
diff --git a/llvm/test/CodeGen/RISCV/rv64m-exhaustive-w-insts.ll b/llvm/test/CodeGen/RISCV/rv64m-exhaustive-w-insts.ll
new file mode 100644
index 0000000..f3e877a
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rv64m-exhaustive-w-insts.ll
@@ -0,0 +1,1308 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s \
+; RUN:   | FileCheck %s -check-prefix=RV64IM
+
+; The patterns for the 'W' suffixed RV64M instructions have the potential of
+; missing cases. This file checks all the variants of
+; sign-extended/zero-extended/any-extended inputs and outputs.
+
+define i32 @aext_mulw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_mulw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_mulw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_mulw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_mulw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_mulw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_mulw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_mulw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_mulw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_mulw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_mulw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mulw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_mulw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_mulw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_mulw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_mulw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_mulw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    mul a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = mul i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a1, a1, 32
+; RV64IM-NEXT:    srli a1, a1, 32
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a1, a1, 32
+; RV64IM-NEXT:    srli a1, a1, 32
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = udiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_divw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_divw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_divw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_divw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_divw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_divw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_divw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_divw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_divw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_divw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_divw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_divw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    divw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = sdiv i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = srem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: aext_remuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define i32 @aext_remuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: aext_remuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: sext_remuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define signext i32 @sext_remuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: sext_remuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_aext_aext(i32 %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remuw_aext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_aext_sext(i32 %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_aext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_aext_zext(i32 %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_aext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    remu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_sext_aext(i32 signext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remuw_sext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_sext_sext(i32 signext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_sext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remuw a0, a0, a1
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_sext_zext(i32 signext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_sext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a0, a0, 32
+; RV64IM-NEXT:    srli a0, a0, 32
+; RV64IM-NEXT:    remu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_zext_aext(i32 zeroext %a, i32 %b) nounwind {
+; RV64IM-LABEL: zext_remuw_zext_aext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a1, a1, 32
+; RV64IM-NEXT:    srli a1, a1, 32
+; RV64IM-NEXT:    remu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_zext_sext(i32 zeroext %a, i32 signext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_zext_sext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    slli a1, a1, 32
+; RV64IM-NEXT:    srli a1, a1, 32
+; RV64IM-NEXT:    remu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
+
+define zeroext i32 @zext_remuw_zext_zext(i32 zeroext %a, i32 zeroext %b) nounwind {
+; RV64IM-LABEL: zext_remuw_zext_zext:
+; RV64IM:       # %bb.0:
+; RV64IM-NEXT:    remu a0, a0, a1
+; RV64IM-NEXT:    ret
+  %1 = urem i32 %a, %b
+  ret i32 %1
+}
-- 
2.7.4